webinar: stop complex fraud in its tracks with neo4j

50
Stop Complex Fraud in its Tracks with Neo4j Neo4j Webinar, March 29, 2017

Upload: neo4j-the-fastest-and-most-scalable-native-graph-database

Post on 11-Apr-2017

237 views

Category:

Technology


3 download

TRANSCRIPT

Page 1: Webinar: Stop Complex Fraud in its Tracks with Neo4j

Stop Complex Fraud in its Tracks with Neo4j

Neo4j Webinar, March 29, 2017

Page 2: Webinar: Stop Complex Fraud in its Tracks with Neo4j

Ryan BoydDeveloper Relations @ Neo4j

Nav Mathur Sr. Director Global Solutions @ Neo4j

Alessandro SvenssonSolutions Marketing @ Neo4j

Page 3: Webinar: Stop Complex Fraud in its Tracks with Neo4j

Agenda• Who are Today’s Fraudsters • How to Fight Fraud Rings with Graphs • Different Types of Credit Card Fraud & Neo4j Demo • How Neo4j Fits in a Typical Architecture • Summary • Q&A

Page 4: Webinar: Stop Complex Fraud in its Tracks with Neo4j

Who Are Today’s Fraudsters?

Page 5: Webinar: Stop Complex Fraud in its Tracks with Neo4j

Organized in groups Synthetic Identities Stolen Identities Hijacked Devices

Who Are Today’s Fraudsters?

Page 6: Webinar: Stop Complex Fraud in its Tracks with Neo4j

Types of Fraud• Credit Card Fraud• Rogue Merchants• Fraud Rings• Insurance Fraud• eCommerce Fraud• Fraud we don’t know about yet…

Page 7: Webinar: Stop Complex Fraud in its Tracks with Neo4j

Digitized and Analog

World of Fraud

Constantly Evolving Few and Many Players

“One Step Ahead”

Simple and Complex

Page 8: Webinar: Stop Complex Fraud in its Tracks with Neo4j

Fraud Detection(From a data-modeling perspective)

Page 9: Webinar: Stop Complex Fraud in its Tracks with Neo4j

Raw Data

Page 10: Webinar: Stop Complex Fraud in its Tracks with Neo4j

Anomalies

Page 11: Webinar: Stop Complex Fraud in its Tracks with Neo4j

Anomalies hidden in “normal behavior”

Page 12: Webinar: Stop Complex Fraud in its Tracks with Neo4j

Patterns

Page 13: Webinar: Stop Complex Fraud in its Tracks with Neo4j

Patterns

Page 14: Webinar: Stop Complex Fraud in its Tracks with Neo4j

1) Detect 2) Respond

Fraud Prevention is About Reacting to Patterns(And doing it fast!)

Page 15: Webinar: Stop Complex Fraud in its Tracks with Neo4j

Relational Database

Choosing Underlying Technology

Page 16: Webinar: Stop Complex Fraud in its Tracks with Neo4j

Data Modelled as a Graph!

Graph Database

Page 17: Webinar: Stop Complex Fraud in its Tracks with Neo4j

Examples of Prevalent Fraud Types

Page 18: Webinar: Stop Complex Fraud in its Tracks with Neo4j
Page 19: Webinar: Stop Complex Fraud in its Tracks with Neo4j

Fraud Rings

Page 20: Webinar: Stop Complex Fraud in its Tracks with Neo4j

“Don’t consider traditional technology adequate to keep

up with criminal trends”

Market Guide for Online Fraud Detection, April 27, 2015

Page 21: Webinar: Stop Complex Fraud in its Tracks with Neo4j

Endpoint-CentricAnalysis of users and their end-points

1.

Navigation CentricAnalysis of navigation behavior and suspect patterns

2.

Account-CentricAnalysis of anomaly behavior by channel

3.

PC:sMobile Phones

IP-addressesUser ID:s

Comparing TransactionIdentity Vetting

Traditional Fraud Detection Methods

Page 22: Webinar: Stop Complex Fraud in its Tracks with Neo4j

Unable to detect • Fraud rings • Fake IP-adresses • Hijacked devices • Synthetic Identities • Stolen Identities • And more…

Weaknesses

DISCRETE ANALYSIS

Endpoint-CentricAnalysis of users and their end-points

1.

Navigation CentricAnalysis of navigation behavior and suspect patterns

2.

Account-CentricAnalysis of anomaly behavior by channel

3.

Traditional Fraud Detection Methods

Page 23: Webinar: Stop Complex Fraud in its Tracks with Neo4j

INVESTIGATE

Revolving Debt

Number of Accounts

INVESTIGATE

Normal behavior

Fraud Detection with Discrete Analysis

Page 24: Webinar: Stop Complex Fraud in its Tracks with Neo4j

Revolving Debt

Number of Accounts

Normal behavior

Fraudulent pattern

Fraud Detection with Connected Analysis

Page 25: Webinar: Stop Complex Fraud in its Tracks with Neo4j

CONNECTED ANALYSIS

Endpoint-CentricAnalysis of users and their end-points

Navigation CentricAnalysis of navigation behavior and suspect patterns

Account-CentricAnalysis of anomaly behavior by channel

DISCRETE ANALYSIS

1. 2. 3.

Cross ChannelAnalysis of anomaly behavior correlated across channels

4.

Entity LinkingAnalysis of relationships to detect organized crime and collusion

5.

Augmented Fraud Detection

Page 26: Webinar: Stop Complex Fraud in its Tracks with Neo4j

ACCOUNT HOLDER 2

Modeling a fraud ring as a graph

ACCOUNT HOLDER 1

ACCOUNT HOLDER 3

Page 27: Webinar: Stop Complex Fraud in its Tracks with Neo4j

ACCOUNT HOLDER 2

ACCOUNT HOLDER 1

ACCOUNT HOLDER 3

CREDIT CARD

BANKACCOUNT

BANKACCOUNT

BANKACCOUNT

PHONE NUMBER

UNSECURED LOAN

SSN 2

UNSECURED LOAN

Modeling a fraud ring as a graph

Page 28: Webinar: Stop Complex Fraud in its Tracks with Neo4j

ACCOUNT HOLDER 2

ACCOUNT HOLDER 1

ACCOUNT HOLDER 3

CREDIT CARD

BANKACCOUNT

BANKACCOUNT

BANKACCOUNT

ADDRESS

PHONE NUMBER

PHONE NUMBER

SSN 2

UNSECURED LOAN

SSN 2

UNSECURED LOAN

Modeling a fraud ring as a graph

Page 29: Webinar: Stop Complex Fraud in its Tracks with Neo4j

Credit Card Fraud

Page 30: Webinar: Stop Complex Fraud in its Tracks with Neo4j

Ryan BoydDeveloper Relations @ Neo4j

Nav Mathur Sr. Director Global Solutions @ Neo4j

Page 31: Webinar: Stop Complex Fraud in its Tracks with Neo4j

Example #1 “Credit Card Testing”

Page 32: Webinar: Stop Complex Fraud in its Tracks with Neo4j

Manual skimming of an ATM

Sophisticated Data Breaches

Retrieval of Credit Card Information

Rogue Merchant

Page 33: Webinar: Stop Complex Fraud in its Tracks with Neo4j

USE

ISSUES

Terminal ATM-skimming

Data Breach

Card Holder

Card Issuer

Fraudster

USE $5MAKES

$10

MAKES

$2MAKES

MAKES $4000

ATTesting

Merchants

ATMAKES Tx

Page 34: Webinar: Stop Complex Fraud in its Tracks with Neo4j

Example #2 “Fraud Origination and

Assessing Loss Magnitude”

Page 35: Webinar: Stop Complex Fraud in its Tracks with Neo4j

TxTx Tx TxTx Tx Tx TxTxTx TxJohn

Page 36: Webinar: Stop Complex Fraud in its Tracks with Neo4j

Tx

$2000

TxTx Tx Tx TxTxTxTx Tx TxComputer

StoreJohn

Page 37: Webinar: Stop Complex Fraud in its Tracks with Neo4j

Tx

$2000

Tx Tx

$25$10$4

TxTx Tx Tx TxTxTxComputer

StoreJohn

Gas Station

Page 38: Webinar: Stop Complex Fraud in its Tracks with Neo4j

Tx

Tx

$2000

Tx Tx

$25$10$4

TxTx Tx Tx TxTxTxComputer

StoreJohn

Gas Station

Sheila Tx

$2

TxTxSheila TxTxTx Tx Tx TxTx

$3000

TxJewelry

StoreTx

$3

Page 39: Webinar: Stop Complex Fraud in its Tracks with Neo4j

Tx

Tx

$2000

Tx Tx

$25$10$4

TxTx Tx Tx TxTxTxComputer

StoreJohn

Gas Station

Sheila Tx

$2

TxTxSheila TxTxTx Tx Tx TxTx

$3000

TxJewelry

StoreTx

$3

Robert TxTxTx Tx TxTx TxTxTx Tx Tx

Page 40: Webinar: Stop Complex Fraud in its Tracks with Neo4j

TxTx

$2

TxTx

Tx

$2000

Tx Tx

$25$10$4

TxTx Tx Tx TxTxTxComputer

StoreJohn

Gas Station

Sheila

Robert

$3

Karen

TxTxTx Tx Tx TxTx

$3000

TxJewelry

StoreTx

$3

TxTxTx Tx Tx TxTx TxTx

TxTx TxTx Tx Tx TxTx

$8 $12

Tx

$1500

Furniture Store

Tx Tx Tx

Page 41: Webinar: Stop Complex Fraud in its Tracks with Neo4j

How Neo4j fits in

Page 42: Webinar: Stop Complex Fraud in its Tracks with Neo4j

Money Transferring

Purchases Bank Services Relational

database

Develop PatternsData Science-team

+ Good for Discrete Analysis– No Holistic View of Data-Relationships– Slow query speed for connections

Page 43: Webinar: Stop Complex Fraud in its Tracks with Neo4j

Money Transferring

Purchases Bank Services Relational

database

Data Lake

+ Good for Map Reduce+ Good for Analytical Workloads– No holistic view– Non-operational workloads– Weeks-to-months processes Develop Patterns

Data Science-team

Merchant Data

Credit Score Data

Other 3rd Party Data

Page 44: Webinar: Stop Complex Fraud in its Tracks with Neo4j

Money Transferring

Purchases Bank Services

Neo4j powers360° view of

transactions in real-time

Neo4j Cluster

SENSETransaction

stream

RESPONDAlerts & notification

LOAD RELEVANT DATA

Relational database

Data Lake

Visualization UI Fine Tune Patterns

Develop PatternsData Science-team

Merchant Data

Credit Score Data

Other 3rd Party Data

Page 45: Webinar: Stop Complex Fraud in its Tracks with Neo4j

Money Transferring

Purchases Bank Services

Neo4j powers360° view of

transactions in real-time

Neo4j Cluster

SENSETransaction

stream

RESPONDAlerts & notification

LOAD RELEVANT DATA

Relational database

Data Lake

Visualization UI Fine Tune Patterns

Develop PatternsData Science-team

Merchant Data

Credit Score Data

Other 3rd Party Data

Data-set used to explore

new insights

Page 46: Webinar: Stop Complex Fraud in its Tracks with Neo4j

Summary

Page 47: Webinar: Stop Complex Fraud in its Tracks with Neo4j

We talked about…Today’s Fraudsters

Examples of different types of Fraud:Fraud Rings

Credit Card Testing Fraud Origination

How Neo4j Fits in an Architecture

Page 48: Webinar: Stop Complex Fraud in its Tracks with Neo4j

Detect & prevent fraud in real-time Faster credit risk analysis and transactions Reduce chargebacks Quickly adapt to new methods of fraud

Why Neo4j? Who’s using it?Financial institutions use Neo4j to:

FINANCE Government Online Retail

Page 49: Webinar: Stop Complex Fraud in its Tracks with Neo4j

Valuable Resources!

neo4jsandbox.com https://neo4j.com/use-cases/fraud-detection/ neo4j.com/product

Sandbox Fraud Detection Product

Page 50: Webinar: Stop Complex Fraud in its Tracks with Neo4j

Q&A